Abstract
In robotic and manufacturing systems, it is difficult to measure the state of systems accurately because of many uncertain factors and noise, and it is very important to estimate the state of systems. We must measure the phenomena of systems by multiple sensors and estimate the state of systems by acquiring information of sensors. However, we can not acquire all of sensor information synchronically, because each sensor has particular sensor information and measuring time. For estimating the state of systems by multiple sensors, a multi-sensor fusion system fusing various sensory information is needed. In this paper, we propose a Recurrent Fuzzy Inference (RFI) with recurrent inputs and apply it to a multi-sensor fusion system for estimating the state of systems. The membership functions of RFI are expressed by Radial Basis Function (RBF) with insensitive ranges. The shape of the membership functions can be adjusted by a learning algorithm. The learning algorithm is based on the steepest descent method and incremental learning which can add new fuzzy rules. The effectiveness of the multi-sensor fusion system using RFI will be shown through a numerical experiment of moving robot and estimation of surface roughness in grinding process.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fukuda, T., Shimojima, K., Arai, F., and Matsuura, H.: Multi-sensor integration system based on fuzzy inference and neural network, Information and Science 71(1,2) (1992), 27–41.
Shimojima, K., Fukuda, T., Arai, F., and Matsuura, H.: Fuzzy inference integrated 3-d measuring system with led displacement sensor and vision system,Intelligent and Fuzzy Systems 1(1) (1993), 63–72.
Linkens, D. A. and Nie, J.: Fuzzified RBF network-based learning control: structure and self-construction, in: IEEE Internat. Conf. on Neural Networks, 1993, pp. 1016–1021.
Shimojima, K., Fukuda, T., Arai, F., and Hasegawa, Y.: Hierarchical control system based on unsupervised fuzzy-neuro system, in: IEEE Internat. Joint Conf. on Neural Networks, 1995, pp. 1403–1408.
Rumelhart, D. E., McClelland, J. L., and the PDP Research Group: Parallel Distributed Processing, Vol. 1, MIT Press, 1986.
Shimojima, K., Fukuda, T., Arai, F., and Hasegawa, Y.: RBF-fuzzy system with ga based unsupervised/ supervised learning method, in: Internat. Joint 4th Fuzzy-IEEE/ 2nd IFES Conf., 1995, pp. 253–258.
Whitley, D., Strakweather, T., and Bogard, C.: Genetic Algorithm and Neural Networks: Optimizing Connection and Connectivity, 1990.
Lee, M. A. and Takagi, H.: Integrating design stages of fuzzy system using genetic algorithm, in: 2nd IEEE Internat. Conf. on Fuzzy Systems, 1993, pp. 612–617.
Fukuda, T., Hasegawa, Y., and Shimojima, K.: Structure optimization of hierarchical fuzzy model using by genetic algorithm, in: 4th IEEE Internat. Conf. on Fuzzy Systems and 2nd Internat. Fuzzy Engineering Symp., 1995, pp. 295–300.
Nomura, H., Hayashi, I., and Wakami, N.: A self-tuning methods of fuzzy control by decent method, in: 4th IFSA Congress on Engineering, 1991, pp. 155–158.
Shimojima, K., Fukuda, T., and Arai, F.: Self-tuning fuzzy inference based spline function, in: 3rd IEEE Internat. Conf. on Fuzzy Systems, 1994, pp. 690–695.
Katayama, R., Kajitani, Y., Kuwata, K., and Nishida, Y.: Self-generating radial basis function as neuro-fuzzy model and its application to nonlinear prediction of chaotic time series, in: 2nd IEEE Internat. Conf. on Fuzzy Systems, 1993, pp. 407–414.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kobayashi, F., Arai, F., Fukuda, T. et al. Sensor Fusion System Using Recurrent Fuzzy Inference. Journal of Intelligent and Robotic Systems 23, 201–216 (1998). https://doi.org/10.1023/A:1008031614352
Issue Date:
DOI: https://doi.org/10.1023/A:1008031614352